Owner

bethgelab

19 indexed repositories · View on GitHub

foolbox
A Python toolbox to create adversarial examples that fool neural networks in PyTorch, TensorFlow, and JAX

Python · 2973 stars
imagecorruptions
Python package to corrupt arbitrary images.

Python · 478 stars
model-vs-human
Benchmark your model on out-of-distribution datasets with carefully collected human comparison data (NeurIPS 2021 Oral)

Python · 363 stars
siamese-mask-rcnn
Siamese Mask R-CNN model for one-shot instance segmentation

Jupyter Notebook · 353 stars
stylize-datasets
A script that applies the AdaIN style transfer method to arbitrary datasets

Python · 166 stars
robustness
Robustness and adaptation of ImageNet scale models. Pre-Release, stay tuned for updates.

Python · 139 stars
openimages2coco
Convert Open Images annotations into MS Coco format to make it a drop in replacement

Jupyter Notebook · 116 stars
frequency_determines_performance
Code for the paper: "No Zero-Shot Without Exponential Data: Pretraining Concept Frequency Determines Multimodal Model Performance" [NeurI...

Jupyter Notebook · 94 stars
sober-reasoning
A Sober Look at Language Model Reasoning

HTML · 92 stars
slow_disentanglement
Towards Nonlinear Disentanglement in Natural Data with Temporal Sparse Coding

Jupyter Notebook · 74 stars
AnalysisBySynthesis
Adversarially Robust Neural Network on MNIST.

Python · 64 stars
adversarial-vision-challenge
NIPS Adversarial Vision Challenge

Python · 41 stars
robust-vision-benchmark
Robust Vision Benchmark

Python · 23 stars
docker
Information and scripts to run and develop the Bethge Lab Docker containers

Makefile · 22 stars
supersanity
A critical analysis of the Cambrian-S model and VSI-Super benchmarks

Python · 16 stars
docker-deeplearning
Development of new unified docker container (WIP)

Python · 9 stars
docker-jupyter-deeplearning
Docker Image with Jupyter for Deep Learning (Caffe, Theano, Lasagne, Keras)

7 stars
alignment-pattern-analysis
Code for the ICLR 2026 paper "Only Brains Align with Brains: Cross-Region Alignment Patterns Expose Limits of Normative Models"

Python · 2 stars
docker-jupyter-notebook
Docker Image with Jupyter Notebook based on bethgelab/docker-xserver

0 stars

Open All

78 open issues indexed

%matplotlib notebook not working anymore Open

bethgelab/docker-jupyter-notebook#1 · 0 comments · 0 reactions · 0 assignees · Indexed Sep 14, 2026
Keras for Python3 Open

bethgelab/docker-jupyter-deeplearning#1 · 0 comments · 0 reactions · 0 assignees · Indexed Sep 14, 2026
boltons Open

bethgelab/docker-jupyter-deeplearning#2 · 0 comments · 0 reactions · 0 assignees · Indexed Sep 14, 2026
Running model performance test locally. Open

bethgelab/robust-vision-benchmark#10 · 0 comments · 0 reactions · 0 assignees · Indexed Sep 14, 2026
local host can't connect to notebooks on fresh install Open

bethgelab/docker#8 · 4 comments · 0 reactions · 0 assignees · Indexed Sep 14, 2026
Relay all HTTP client related errors to the evaluators through crowdAINotifier Open

bethgelab/adversarial-vision-challenge#21 · 0 comments · 0 reactions · 1 assignee · Indexed Sep 14, 2026
Add evaluation functions (+ docs) in this repository Open

bethgelab/adversarial-vision-challenge#22 · 0 comments · 0 reactions · 0 assignees · Indexed Sep 14, 2026
monitor the GPU utilization and gives a warning if it's below XX% Open

enhancement

bethgelab/adversarial-vision-challenge#25 · 0 comments · 0 reactions · 0 assignees · Indexed Sep 14, 2026
Compute Model Statistics Open

bethgelab/adversarial-vision-challenge#26 · 0 comments · 0 reactions · 0 assignees · Indexed Sep 14, 2026
Test for "real attack" against "real model" Open

enhancement

bethgelab/adversarial-vision-challenge#29 · 0 comments · 0 reactions · 0 assignees · Indexed Sep 14, 2026
avc-test-model does not release GPU memory after testing Open

bethgelab/adversarial-vision-challenge#38 · 0 comments · 0 reactions · 0 assignees · Indexed Sep 14, 2026
Can't reach model server. Open

bethgelab/adversarial-vision-challenge#39 · 9 comments · 0 reactions · 0 assignees · Indexed Sep 14, 2026
HTTPResponse' object has no attribute 'findAll' Open

bethgelab/adversarial-vision-challenge#48 · 0 comments · 0 reactions · 0 assignees · Indexed Sep 14, 2026
jupyter extensions Open

bethgelab/docker-deeplearning#3 · 0 comments · 0 reactions · 0 assignees · Indexed Sep 14, 2026
juptyer password Open

bethgelab/docker-deeplearning#4 · 0 comments · 0 reactions · 0 assignees · Indexed Sep 14, 2026
document usage in README Open

bethgelab/docker-deeplearning#6 · 0 comments · 1 reaction · 0 assignees · Indexed Sep 14, 2026
Tensorboard on cudnn6 container fails Open

bethgelab/docker-deeplearning#14 · 0 comments · 2 reactions · 0 assignees · Indexed Sep 14, 2026
Update Mask_RCNN Open

enhancement

bethgelab/siamese-mask-rcnn#5 · 0 comments · 0 reactions · 0 assignees · Indexed Sep 14, 2026
Results Open

bethgelab/siamese-mask-rcnn#17 · 5 comments · 0 reactions · 0 assignees · Indexed Sep 14, 2026
Problem with mask predictions Open

bethgelab/siamese-mask-rcnn#22 · 17 comments · 0 reactions · 0 assignees · Indexed Sep 14, 2026
Problem with custom dataset Open

bethgelab/siamese-mask-rcnn#28 · 8 comments · 0 reactions · 0 assignees · Indexed Sep 14, 2026
Test.ipynb Open

bethgelab/siamese-mask-rcnn#32 · 0 comments · 0 reactions · 0 assignees · Indexed Sep 14, 2026
One-Shot Detection - input_target shape Error Open

bethgelab/siamese-mask-rcnn#33 · 3 comments · 0 reactions · 0 assignees · Indexed Sep 14, 2026
TypeError: unhashable type: 'ListWrapper' when try to train model Open

bethgelab/siamese-mask-rcnn#34 · 1 comment · 0 reactions · 0 assignees · Indexed Sep 14, 2026
issue re-running Open

bethgelab/siamese-mask-rcnn#35 · 0 comments · 0 reactions · 0 assignees · Indexed Sep 14, 2026
Loading weights Open

bethgelab/siamese-mask-rcnn#37 · 0 comments · 0 reactions · 0 assignees · Indexed Sep 14, 2026
Why are model loading and inference times so slow? Open

bethgelab/siamese-mask-rcnn#38 · 0 comments · 0 reactions · 0 assignees · Indexed Sep 14, 2026
skimage could be problematic Open

bethgelab/openimages2coco#2 · 0 comments · 0 reactions · 0 assignees · Indexed Sep 14, 2026
Wrong processing logic to get annotated_attributes Open

bethgelab/openimages2coco#4 · 0 comments · 0 reactions · 0 assignees · Indexed Sep 14, 2026
Are these lines correct? Open

bethgelab/openimages2coco#6 · 0 comments · 2 reactions · 0 assignees · Indexed Sep 14, 2026
Stylised images have problems Open

bethgelab/stylize-datasets#22 · 2 comments · 0 reactions · 0 assignees · Indexed Sep 14, 2026
TypeError: configurable() got an unexpected keyword argument 'blacklist' Open

bethgelab/slow_disentanglement#6 · 0 comments · 0 reactions · 0 assignees · Indexed Sep 14, 2026
The download link for the ‘mpi3d_toy’ dataset appears to be broken or inactive Open

bethgelab/slow_disentanglement#7 · 0 comments · 0 reactions · 0 assignees · Indexed Sep 14, 2026
Really slow attacks with demo code Open

bethgelab/AnalysisBySynthesis#1 · 3 comments · 3 reactions · 0 assignees · Indexed Sep 14, 2026
About training code Open

bethgelab/AnalysisBySynthesis#4 · 4 comments · 0 reactions · 0 assignees · Indexed Sep 14, 2026
Could you share the code to evaluate your model? Open

bethgelab/AnalysisBySynthesis#6 · 4 comments · 2 reactions · 0 assignees · Indexed Sep 14, 2026
Error while using \scripts\attacks.py" Open

bethgelab/AnalysisBySynthesis#10 · 2 comments · 0 reactions · 0 assignees · Indexed Sep 14, 2026
AttributeError: 'PyTorchModel' object has no attribute 'predictions' Open

bethgelab/AnalysisBySynthesis#11 · 0 comments · 0 reactions · 0 assignees · Indexed Sep 14, 2026
Train all parameters or only BN layers Open

bethgelab/robustness#14 · 0 comments · 0 reactions · 0 assignees · Indexed Sep 14, 2026
ImageNet classname (updated to add projectile and sunglass) Open

bethgelab/frequency_determines_performance#1 · 0 comments · 0 reactions · 0 assignees · Indexed Sep 14, 2026
BiT models via timm? Open

bethgelab/model-vs-human#12 · 0 comments · 0 reactions · 0 assignees · Indexed Sep 14, 2026
Feature request: Simpler loading of custom models Open

enhancement

bethgelab/model-vs-human#14 · 2 comments · 0 reactions · 0 assignees · Indexed Sep 14, 2026
Feature request: Machine readable results, e.g. CSV Open

enhancement

bethgelab/model-vs-human#15 · 1 comment · 0 reactions · 0 assignees · Indexed Sep 14, 2026
motion_blur still fails on input of size 32x32x3 Open

bug

bethgelab/imagecorruptions#13 · 0 comments · 0 reactions · 0 assignees · Indexed Sep 14, 2026
Most corruptions fail on Cifar dataset with size 32 x 32 x 3 Open

bethgelab/imagecorruptions#21 · 0 comments · 0 reactions · 0 assignees · Indexed Sep 14, 2026
TypeError: gaussian() got an unexpected keyword argument 'multichannel' Open

bethgelab/imagecorruptions#30 · 1 comment · 5 reactions · 0 assignees · Indexed Sep 14, 2026
Model request Open

model request

bethgelab/sober-reasoning#12 · 0 comments · 0 reactions · 0 assignees · Indexed Sep 14, 2026
Model Request: One Shot RLVR Open

model request

bethgelab/sober-reasoning#14 · 0 comments · 0 reactions · 0 assignees · Indexed Sep 14, 2026
Separate SFT+RL from RL only Open

enhancement

bethgelab/sober-reasoning#17 · 1 comment · 0 reactions · 0 assignees · Indexed Sep 14, 2026
The code (command) to reproduce the official benchmark Open

bethgelab/sober-reasoning#18 · 1 comment · 0 reactions · 0 assignees · Indexed Sep 14, 2026

bethgelab

Get new issues in your inbox